Real‐time vision‐based detection of Rumex obtusifolius in grassland

Abstract

Rumex obtusifolius is a common grassland weed that is hard to control in a non-chemical way. The objective of our research was to automate the detection of R. obtusifolius as a step towards fully automated mechanical control of the weed. We have developed a vision-based system that uses textural analysis to detect R. obtusifolius against a grass background. Image sections are classified as grass or weed using 2-D Fourier analysis. We conducted two experiments. In the first (laboratory) experiment, we collected 28 images containing R. obtusifolius and 28 images containing only grass. Between 23 and 25 of 28 images were correctly classified (82-89%) as showing R. obtusifolius; all grass images were correctly classified as such. In the second (field) experiment, a self-propelled platform was used to obtain five sequences of images of R. obtusifolius plants.We used the parameters that gave the best classification results in the first experiment. We found, after changing one of the algorithmÕs parameters in response to prevailing light conditions, that we were able to detect R. obtusifolius in each image of each sequence. The algorithm scans a ground area of 1.5 m 2 in 30 ms. We conclude that the algorithm developed is sufficiently fast and robust to eventually serve as a basis for a practical robot to detect and control R. obtusifolius in grassland.

Effects of nutrient availability on performance and mortality of Rumex obtusifolius and R. crispus in unmanaged grassland

“…obtusifolius L. (broad-leaved dock, hereafter referred to as R. obtusifolius) in temperate grasslands has received high research attention (Zaller 2004(Zaller , 2006Bayhan et al 2006;Van Evert et al 2009;Gilgen et al 2010;Stilmant et al 2010;Strnad et al 2010;Hrdličková et al 2011;Hann et al 2012). This is because R. obtusifolius is considered to be one of the most troublesome grassland weedy species worldwide due to: (1) its general avoidance by grazing livestock, especially cattle and horses; (2) its negative effects on forage quality, as it induces health problems if eaten in high quantity and (3) its negative effects on biomass production of desired forage species by competition for space, water and nutrients (Zaller 2004).…”

A robot to detect and control broad‐leaved dock (Rumex obtusifolius L.) in grassland

“…Detection of broad-leaved dock in grassland pasture has been studied by Dürr, Anken, Bollhalder, Sauter, Burri, et al (2004), Gebhardt and Kühbauch (2007), Gebhardt, Schellberg, Lock, and Kühbauch (2006), Holpp, Anken,Šeatović, Grüninger, and Hüppi (2008),Šeatović (2008),Šeatović, Kutterer, Anken, and Holpp (2009), and Van Evert, Polder, Van der Heijden, Kempenaar, and Lotz (2009. In addition, texture-based discrimination between grassy and broad-leaved weeds on a soil background was described by Ishak, Hussain, and Mustafa (2009) and by Tang, Tian, and Steward (2003).…”

Targeted and Microdose Chemical Applications

“…The use of sensors and computers to quickly assess plants and their location within a field has led to the development of various systems. For example, a vision-based system was developed for broadleaf dock (Rumex obtusifolius L.) in grasslands using 2-D Fourier analysis to classify images (van Evert et al 2009). Algorithms from the classified images successfully detected broadleaf dock in each image sequence covering an area of 1.5 m 2 every 30 milliseconds.…”